The Agent Skills Directory

[Prompt Injection] (SAFE): No instructions found that attempt to bypass AI safety filters or override system prompts. The instructional tone is standard for specialized agent skills.
[Data Exposure & Exfiltration] (SAFE): No hardcoded credentials or sensitive file access patterns were identified. The skill correctly recommends using native secure storage (Keychain/KeyStore) for authentication tokens.
[Remote Code Execution] (SAFE): No patterns for downloading or executing code from untrusted remote sources were detected. Reference files and assets are internal to the skill directory.
[Obfuscation] (SAFE): The content is clear markdown and code without any encoding (Base64), zero-width characters, or homoglyphs.
[Security Practices] (SAFE): The skill explicitly includes a section on security patterns (Token storage, certificate pinning, encryption, OWASP), which aligns with industry best practices.

alloy-expert